Lunderberg opened a new pull request, #12925: URL: https://github.com/apache/tvm/pull/12925
Previously, a python int/float would be converted to a TIR int32/float32 in `tvm.runtime.convert`. These types may not match the buffer's type, even though it is the closest Python representation of the buffer's type. Therefore, the `pad_value` should be preferentially converted to the matching type of the buffer. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
